ClaudeBot/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-17 20:31:47 +02:00
Code Issues Packages Projects Releases Wiki Activity

laguna: use n_ff_exp_impl for the uniform-MoE FFN size

Browse Source 
Laguna landed after this branch was cut and reads hparams.n_ff_exp as a
scalar. This series turns it into a per-layer array with an n_ff_exp(il)
accessor, so the three scalar reads no longer compile. Laguna is a
uniform MoE, so point them at the scalar fallback n_ff_exp_impl, same as
deepseek2/qwen3moe/gemma4 in this series. No behaviour change.
This commit is contained in:
Yaniss
2026-07-26 12:43:51 +02:00
parent 189b67fc2c
commit dbedc9e19c
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/laguna.cpp
+3 -3
View File
@@ -9,7 +9,7 @@
void llama_model_laguna::load_arch_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
ml.get_key(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead);
ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp);
ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp_impl);
ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func, false);
ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale, false);
ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm, false);
@@ -24,7 +24,7 @@ void llama_model_laguna::load_arch_hparams(llama_model_loader & ml) {
// Weightless fixtures (test-llama-archs) omit this key; derive a nonzero
// size so the shared expert is still built. Real GGUFs always carry the
// exact value (routed and shared FF lengths may differ).
hparams.n_ff_shexp = hparams.n_ff_exp * hparams.n_expert_shared;
hparams.n_ff_shexp = hparams.n_ff_exp_impl * hparams.n_expert_shared;
}
// Sliding-window attention is OPTIONAL. XS.2 is hybrid (full / SWA / SWA /
@@ -75,7 +75,7 @@ void llama_model_laguna::load_arch_tensors(llama_model_loader & ml) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
}
const int64_t n_ff_exp = hparams.n_ff_exp;
const int64_t n_ff_exp = hparams.n_ff_exp_impl;
const int64_t n_ff_shexp = hparams.n_ff_shexp;
for (int i = 0; i < n_layer; ++i) {